scylla 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +0 -1
- data/Gemfile.lock +0 -10
- data/README.rdoc +22 -0
- data/VERSION +1 -1
- data/bin/scylla +13 -0
- data/lib/scylla/classifier.rb +2 -2
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +400 -0
- data/lib/scylla/lms/afrikaans.lm +400 -0
- data/lib/scylla/lms/arabic.lm +400 -0
- data/lib/scylla/lms/bulgarian.lm +400 -0
- data/lib/scylla/lms/catalan.lm +400 -0
- data/lib/scylla/lms/chinese.lm +400 -0
- data/lib/scylla/lms/danish.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -0
- data/lib/scylla/lms/esperanto.lm +400 -0
- data/lib/scylla/lms/finnish.lm +400 -0
- data/lib/scylla/lms/french.lm +400 -0
- data/lib/scylla/lms/german.lm +400 -0
- data/lib/scylla/lms/greek-iso8859-7.lm +400 -0
- data/lib/scylla/lms/hebrew.lm +400 -0
- data/lib/scylla/lms/hindi.lm +400 -0
- data/lib/scylla/lms/hungarian.lm +400 -0
- data/lib/scylla/lms/icelandic.lm +400 -0
- data/lib/scylla/lms/indonesian.lm +400 -0
- data/lib/scylla/lms/irish.lm +400 -0
- data/lib/scylla/lms/italian.lm +400 -0
- data/lib/scylla/lms/japanese.lm +400 -0
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -0
- data/lib/scylla/lms/latin.lm +400 -0
- data/lib/scylla/lms/malay.lm +400 -0
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/mingo.lm +400 -0
- data/lib/scylla/lms/nepali.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -0
- data/lib/scylla/lms/portuguese.lm +400 -0
- data/lib/scylla/lms/quechua.lm +400 -0
- data/lib/scylla/lms/romanian.lm +400 -0
- data/lib/scylla/lms/rumantsch.lm +400 -0
- data/lib/scylla/lms/russian.lm +400 -0
- data/lib/scylla/lms/sanskrit.lm +400 -0
- data/lib/scylla/lms/scots_gaelic.lm +400 -0
- data/lib/scylla/lms/serbian-ascii.lm +400 -0
- data/lib/scylla/lms/slovak-ascii.lm +400 -0
- data/lib/scylla/lms/slovenian-ascii.lm +400 -0
- data/lib/scylla/lms/spanish.lm +400 -0
- data/lib/scylla/lms/swahili.lm +400 -0
- data/lib/scylla/lms/swedish.lm +400 -0
- data/lib/scylla/lms/tagalog.lm +400 -0
- data/lib/scylla/lms/tamil.lm +400 -0
- data/lib/scylla/lms/thai.lm +400 -0
- data/lib/scylla/lms/turkish.lm +400 -0
- data/lib/scylla/lms/ukrainian-koi8_u.lm +400 -0
- data/lib/scylla/lms/vietnamese.lm +400 -0
- data/lib/scylla/lms/welsh.lm +400 -0
- data/lib/scylla/lms/yiddish-utf.lm +400 -0
- data/lib/scylla/loader.rb +8 -1
- data/scylla-0.1.0.gem +0 -0
- data/scylla.gemspec +69 -3
- data/source_texts/kannada.txt +283 -0
- data/test/classifier_test.rb +7 -0
- data/test/fixtures/lms/13375p33k.lm +400 -0
- data/test/fixtures/lms/danish.lm +400 -0
- data/test/fixtures/lms/english.lm +400 -0
- data/test/fixtures/lms/french.lm +400 -0
- data/test/fixtures/lms/german.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -0
- data/test/fixtures/lms/kannada.lm +400 -0
- data/test/fixtures/lms/spanish.lm +400 -0
- data/test/fixtures/source_texts/13375P33K.txt +199 -0
- data/test/fixtures/source_texts/japanese.txt +199 -0
- data/test/fixtures/source_texts/kannada.txt +283 -0
- data/test/generator_test.rb +10 -7
- data/test/helper.rb +5 -6
- data/test/loader_test.rb +1 -0
- data/test/scylla_test.rb +1 -0
- metadata +78 -14
- data/source_texts/armenian.txt +0 -86
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 39275
|
2
|
+
a 10584
|
3
|
+
e 10526
|
4
|
+
o 7129
|
5
|
+
n 6382
|
6
|
+
s 6107
|
7
|
+
i 5947
|
8
|
+
r 5605
|
9
|
+
l 5112
|
10
|
+
d 4622
|
11
|
+
t 3867
|
12
|
+
c 3674
|
13
|
+
a_ 2987
|
14
|
+
e_ 2942
|
15
|
+
u 2914
|
16
|
+
� 2572
|
17
|
+
s_ 2497
|
18
|
+
de 2468
|
19
|
+
__ 2421
|
20
|
+
_d 2335
|
21
|
+
p 2303
|
22
|
+
m 2195
|
23
|
+
_de 2098
|
24
|
+
o_ 1869
|
25
|
+
_e 1761
|
26
|
+
n_ 1759
|
27
|
+
en 1746
|
28
|
+
de_ 1681
|
29
|
+
_de_ 1604
|
30
|
+
la 1459
|
31
|
+
es 1454
|
32
|
+
_l 1371
|
33
|
+
, 1276
|
34
|
+
,_ 1266
|
35
|
+
l_ 1224
|
36
|
+
os 1221
|
37
|
+
er 1194
|
38
|
+
on 1122
|
39
|
+
as 1103
|
40
|
+
ci 1095
|
41
|
+
_p 1071
|
42
|
+
el 1049
|
43
|
+
_c 1043
|
44
|
+
an 1032
|
45
|
+
ra 1018
|
46
|
+
al 997
|
47
|
+
g 941
|
48
|
+
_la 932
|
49
|
+
os_ 931
|
50
|
+
nt 926
|
51
|
+
te 922
|
52
|
+
co 901
|
53
|
+
b 896
|
54
|
+
_a 893
|
55
|
+
re 888
|
56
|
+
ta 858
|
57
|
+
ri 825
|
58
|
+
ad 825
|
59
|
+
ar 816
|
60
|
+
la_ 814
|
61
|
+
or 812
|
62
|
+
el_ 796
|
63
|
+
_s 795
|
64
|
+
. 766
|
65
|
+
pa 757
|
66
|
+
� 756
|
67
|
+
ó 755
|
68
|
+
do 751
|
69
|
+
st 737
|
70
|
+
ro 725
|
71
|
+
y 717
|
72
|
+
as_ 716
|
73
|
+
_la_ 712
|
74
|
+
na 691
|
75
|
+
ue 688
|
76
|
+
v 663
|
77
|
+
in 658
|
78
|
+
_en 644
|
79
|
+
ca 643
|
80
|
+
ic 635
|
81
|
+
en_ 632
|
82
|
+
es_ 621
|
83
|
+
da 621
|
84
|
+
ia 620
|
85
|
+
E 615
|
86
|
+
to 609
|
87
|
+
lo 605
|
88
|
+
_m 597
|
89
|
+
f 596
|
90
|
+
_co 590
|
91
|
+
y_ 563
|
92
|
+
� 557
|
93
|
+
í 557
|
94
|
+
_el 553
|
95
|
+
ti 535
|
96
|
+
no 532
|
97
|
+
_en_ 529
|
98
|
+
._ 524
|
99
|
+
_y 523
|
100
|
+
un 513
|
101
|
+
ent 513
|
102
|
+
le 507
|
103
|
+
_el_ 505
|
104
|
+
r_ 500
|
105
|
+
io 495
|
106
|
+
_y_ 493
|
107
|
+
�n 488
|
108
|
+
ón 488
|
109
|
+
i� 487
|
110
|
+
po 475
|
111
|
+
a� 472
|
112
|
+
_E 470
|
113
|
+
se 468
|
114
|
+
sp 460
|
115
|
+
q 456
|
116
|
+
qu 455
|
117
|
+
� 453
|
118
|
+
ñ 453
|
119
|
+
C 451
|
120
|
+
tr 450
|
121
|
+
_t 444
|
122
|
+
ma 440
|
123
|
+
id 432
|
124
|
+
ac 431
|
125
|
+
ió 428
|
126
|
+
is 427
|
127
|
+
ni 426
|
128
|
+
om 425
|
129
|
+
ne 414
|
130
|
+
nte 414
|
131
|
+
con 410
|
132
|
+
do_ 407
|
133
|
+
nc 406
|
134
|
+
_r 403
|
135
|
+
li 403
|
136
|
+
nd 403
|
137
|
+
ie 401
|
138
|
+
si 399
|
139
|
+
me 396
|
140
|
+
añ 395
|
141
|
+
á 391
|
142
|
+
� 391
|
143
|
+
h 383
|
144
|
+
pr 382
|
145
|
+
�n_ 376
|
146
|
+
ón_ 376
|
147
|
+
spa 375
|
148
|
+
_C 375
|
149
|
+
que 374
|
150
|
+
ión 373
|
151
|
+
ue_ 370
|
152
|
+
pa� 363
|
153
|
+
ec 341
|
154
|
+
mi 340
|
155
|
+
ión_ 339
|
156
|
+
_con 338
|
157
|
+
_re 336
|
158
|
+
rt 336
|
159
|
+
di 336
|
160
|
+
pe 333
|
161
|
+
_pr 328
|
162
|
+
A 327
|
163
|
+
te_ 327
|
164
|
+
que_ 324
|
165
|
+
_q 319
|
166
|
+
_qu 319
|
167
|
+
it 317
|
168
|
+
pañ 315
|
169
|
+
Es 313
|
170
|
+
_se 310
|
171
|
+
mo 310
|
172
|
+
_lo 309
|
173
|
+
spañ 309
|
174
|
+
spa� 309
|
175
|
+
_que 308
|
176
|
+
_po 307
|
177
|
+
los 305
|
178
|
+
_es 304
|
179
|
+
al_ 303
|
180
|
+
ol 302
|
181
|
+
aci 300
|
182
|
+
ci� 300
|
183
|
+
ció 299
|
184
|
+
los_ 296
|
185
|
+
I 295
|
186
|
+
a, 294
|
187
|
+
ado 294
|
188
|
+
ur 293
|
189
|
+
a,_ 292
|
190
|
+
_que_ 291
|
191
|
+
_i 291
|
192
|
+
ción 285
|
193
|
+
_Es 283
|
194
|
+
su 282
|
195
|
+
ña 278
|
196
|
+
�a 278
|
197
|
+
z 275
|
198
|
+
_f 275
|
199
|
+
_u 271
|
200
|
+
ica 271
|
201
|
+
on_ 270
|
202
|
+
del 270
|
203
|
+
cia 267
|
204
|
+
ce 267
|
205
|
+
_del 266
|
206
|
+
del_ 261
|
207
|
+
� 261
|
208
|
+
é 261
|
209
|
+
nci 260
|
210
|
+
_del_ 259
|
211
|
+
tu 258
|
212
|
+
_o 258
|
213
|
+
_h 257
|
214
|
+
_los 257
|
215
|
+
or_ 256
|
216
|
+
am 255
|
217
|
+
_los_ 254
|
218
|
+
sta 253
|
219
|
+
_un 252
|
220
|
+
Espa 250
|
221
|
+
Espa� 250
|
222
|
+
Esp 250
|
223
|
+
ra_ 249
|
224
|
+
s, 249
|
225
|
+
s,_ 248
|
226
|
+
est 245
|
227
|
+
ll 245
|
228
|
+
ab 245
|
229
|
+
las 244
|
230
|
+
por 244
|
231
|
+
ía 243
|
232
|
+
�a 243
|
233
|
+
aña 243
|
234
|
+
at 239
|
235
|
+
r� 239
|
236
|
+
so 234
|
237
|
+
paña 234
|
238
|
+
_A 233
|
239
|
+
im 231
|
240
|
+
_a_ 231
|
241
|
+
las_ 230
|
242
|
+
ns 228
|
243
|
+
_Esp 227
|
244
|
+
_Espa 227
|
245
|
+
cu 226
|
246
|
+
em 226
|
247
|
+
na_ 224
|
248
|
+
j 224
|
249
|
+
ul 220
|
250
|
+
ant 219
|
251
|
+
P 219
|
252
|
+
ente 218
|
253
|
+
rr 218
|
254
|
+
to_ 217
|
255
|
+
nte_ 217
|
256
|
+
) 216
|
257
|
+
( 216
|
258
|
+
_n 216
|
259
|
+
dad 215
|
260
|
+
ia_ 215
|
261
|
+
se_ 215
|
262
|
+
_( 214
|
263
|
+
il 213
|
264
|
+
vi 213
|
265
|
+
L 211
|
266
|
+
ter 209
|
267
|
+
_pa 206
|
268
|
+
ada 205
|
269
|
+
men 203
|
270
|
+
era 202
|
271
|
+
ran 201
|
272
|
+
les 201
|
273
|
+
da_ 200
|
274
|
+
ig 198
|
275
|
+
_su 198
|
276
|
+
o, 197
|
277
|
+
o,_ 195
|
278
|
+
ien 195
|
279
|
+
tra 193
|
280
|
+
res 192
|
281
|
+
cio 190
|
282
|
+
com 190
|
283
|
+
one 189
|
284
|
+
_ca 189
|
285
|
+
ida 189
|
286
|
+
M 188
|
287
|
+
S 187
|
288
|
+
ed 187
|
289
|
+
t� 185
|
290
|
+
_las 185
|
291
|
+
m� 185
|
292
|
+
ona 185
|
293
|
+
_las_ 185
|
294
|
+
ha 184
|
295
|
+
ion 184
|
296
|
+
nes 183
|
297
|
+
no_ 182
|
298
|
+
od 182
|
299
|
+
ale 180
|
300
|
+
_P 179
|
301
|
+
br 178
|
302
|
+
sa 178
|
303
|
+
_com 178
|
304
|
+
_por 177
|
305
|
+
mp 177
|
306
|
+
bi 176
|
307
|
+
_in 176
|
308
|
+
pro 175
|
309
|
+
ist 175
|
310
|
+
ació 173
|
311
|
+
dos 173
|
312
|
+
aci� 173
|
313
|
+
ct 172
|
314
|
+
des 172
|
315
|
+
oc 172
|
316
|
+
eg 167
|
317
|
+
_I 167
|
318
|
+
_al 167
|
319
|
+
an_ 166
|
320
|
+
por_ 166
|
321
|
+
ero 165
|
322
|
+
_pro 164
|
323
|
+
_por_ 164
|
324
|
+
_se_ 164
|
325
|
+
ía_ 163
|
326
|
+
ño 163
|
327
|
+
�a_ 163
|
328
|
+
�o 163
|
329
|
+
_v 162
|
330
|
+
va 161
|
331
|
+
ment 161
|
332
|
+
lo_ 160
|
333
|
+
iv 160
|
334
|
+
gu 159
|
335
|
+
ndo 159
|
336
|
+
mu 158
|
337
|
+
_. 157
|
338
|
+
_si 156
|
339
|
+
et 156
|
340
|
+
ici 155
|
341
|
+
fi 155
|
342
|
+
d_ 155
|
343
|
+
go 154
|
344
|
+
ria 154
|
345
|
+
_M 153
|
346
|
+
a. 152
|
347
|
+
ron 152
|
348
|
+
mo_ 152
|
349
|
+
ga 151
|
350
|
+
ones 151
|
351
|
+
_ha 151
|
352
|
+
op 151
|
353
|
+
za 151
|
354
|
+
_L 150
|
355
|
+
us 150
|
356
|
+
_S 149
|
357
|
+
mb 149
|
358
|
+
ca_ 148
|
359
|
+
ba 148
|
360
|
+
año 148
|
361
|
+
Ca 148
|
362
|
+
sti 147
|
363
|
+
_pe 147
|
364
|
+
ado_ 147
|
365
|
+
ncia 147
|
366
|
+
ua 146
|
367
|
+
uc 146
|
368
|
+
ico 146
|
369
|
+
nes_ 145
|
370
|
+
s. 144
|
371
|
+
ña_ 144
|
372
|
+
�a_ 144
|
373
|
+
ve 144
|
374
|
+
rio 143
|
375
|
+
cion 143
|
376
|
+
_con_ 142
|
377
|
+
con_ 142
|
378
|
+
_._ 142
|
379
|
+
ente_ 142
|
380
|
+
ip 141
|
381
|
+
rc 141
|
382
|
+
io_ 140
|
383
|
+
ntr 140
|
384
|
+
nto 139
|
385
|
+
tor 139
|
386
|
+
_g 138
|
387
|
+
ob 138
|
388
|
+
ta_ 138
|
389
|
+
par 138
|
390
|
+
G 137
|
391
|
+
ir 137
|
392
|
+
aña_ 136
|
393
|
+
bl 136
|
394
|
+
n� 136
|
395
|
+
ante 136
|
396
|
+
dos_ 135
|
397
|
+
ó_ 134
|
398
|
+
�_ 134
|
399
|
+
eri 134
|
400
|
+
err 134
|